Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical/scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disturbed
    -0.08
    (Query
    -0.08
     Winn
    -0.08
    بادل
    -0.08
     provoca
    -0.08
     provo
    -0.07
    abla
    -0.07
     bou
    -0.07
     flott
    -0.07
    न्ज
    -0.07
    POSITIVE LOGITS
     Sheriff's
    0.09
    币
    0.08
     apostles
    0.08
    ánu
    0.08
    atel
    0.07
    犯罪
    0.07
    irati
    0.07
     scrutiny
    0.07
     felony
    0.07
     artesanal
    0.07
    Act Density 0.038%

    No Known Activations